open-llm-leaderboard-old/details_jeiku__Chaos_RP_l3_8B
收藏数据集概述
该数据集是在评估模型 jeiku/Chaos_RP_l3_8B 在 Open LLM Leaderboard 上的运行过程中自动创建的。
数据集组成
- 数据集包含 63 个配置，每个配置对应一个评估任务。
- 数据集从 1 次运行中创建。每次运行可以在每个配置中找到特定的分割，分割名称使用运行的时间戳。
- "train" 分割始终指向最新的结果。
- 额外的 "results" 配置存储所有运行的聚合结果，用于计算和显示 Open LLM Leaderboard 上的聚合指标。
数据加载示例
python from datasets import load_dataset data = load_dataset("open-llm-leaderboard/details_jeiku__Chaos_RP_l3_8B", "harness_winogrande_5", split="train")
最新结果
以下是 最新结果来自 run 2024-04-23T03:28:09.770830：
python { "all": { "acc": 0.6491408443077877, "acc_stderr": 0.03180472169747596, "acc_norm": 0.6622109711783685, "acc_norm_stderr": 0.0326579366811438, "mc1": 0.37209302325581395, "mc1_stderr": 0.016921090118814035, "mc2": 0.5100950170127121, "mc2_stderr": 0.015947208481945325 }, "harness|arc:challenge|25": { "acc": 0.5844709897610921, "acc_stderr": 0.014401366641216393, "acc_norm": 0.6126279863481229, "acc_norm_stderr": 0.014235872487909874 }, "harness|hellaswag|10": { "acc": 0.5997809201354312, "acc_stderr": 0.0048894131262087765, "acc_norm": 0.7856004779924318, "acc_norm_stderr": 0.0040956637319592175 }, "harness|hendrycksTest-abstract_algebra|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-anatomy|5": { "acc": 0.6074074074074074, "acc_stderr": 0.04218506215368879, "acc_norm": 0.6074074074074074, "acc_norm_stderr": 0.04218506215368879 }, "harness|hendrycksTest-astronomy|5": { "acc": 0.6973684210526315, "acc_stderr": 0.03738520676119667, "acc_norm": 0.6973684210526315, "acc_norm_stderr": 0.03738520676119667 }, "harness|hendrycksTest-business_ethics|5": { "acc": 0.67, "acc_stderr": 0.047258156262526094, "acc_norm": 0.67, "acc_norm_stderr": 0.047258156262526094 }, "harness|hendrycksTest-clinical_knowledge|5": { "acc": 0.7396226415094339, "acc_stderr": 0.027008766090708035, "acc_norm": 0.7396226415094339, "acc_norm_stderr": 0.027008766090708035 }, "harness|hendrycksTest-college_biology|5": { "acc": 0.7916666666666666, "acc_stderr": 0.033961162058453336, "acc_norm": 0.7916666666666666, "acc_norm_stderr": 0.033961162058453336 }, "harness|hendrycksTest-college_chemistry|5": { "acc": 0.48, "acc_stderr": 0.050211673156867795, "acc_norm": 0.48, "acc_norm_stderr": 0.050211673156867795 }, "harness|hendrycksTest-college_computer_science|5": { "acc": 0.55, "acc_stderr": 0.049999999999999996, "acc_norm": 0.55, "acc_norm_stderr": 0.049999999999999996 }, "harness|hendrycksTest-college_mathematics|5": { "acc": 0.39, "acc_stderr": 0.04902071300001975, "acc_norm": 0.39, "acc_norm_stderr": 0.04902071300001975 }, "harness|hendrycksTest-college_medicine|5": { "acc": 0.6473988439306358, "acc_stderr": 0.036430371689585475, "acc_norm": 0.6473988439306358, "acc_norm_stderr": 0.036430371689585475 }, "harness|hendrycksTest-college_physics|5": { "acc": 0.46078431372549017, "acc_stderr": 0.04959859966384181, "acc_norm": 0.46078431372549017, "acc_norm_stderr": 0.04959859966384181 }, "harness|hendrycksTest-computer_security|5": { "acc": 0.78, "acc_stderr": 0.04163331998932263, "acc_norm": 0.78, "acc_norm_stderr": 0.04163331998932263 }, "harness|hendrycksTest-conceptual_physics|5": { "acc": 0.5617021276595745, "acc_stderr": 0.03243618636108102, "acc_norm": 0.5617021276595745, "acc_norm_stderr": 0.03243618636108102 }, "harness|hendrycksTest-econometrics|5": { "acc": 0.4824561403508772, "acc_stderr": 0.04700708033551038, "acc_norm": 0.4824561403508772, "acc_norm_stderr": 0.04700708033551038 }, "harness|hendrycksTest-electrical_engineering|5": { "acc": 0.6275862068965518, "acc_stderr": 0.0402873153294756, "acc_norm": 0.6275862068965518, "acc_norm_stderr": 0.0402873153294756 }, "harness|hendrycksTest-elementary_mathematics|5": { "acc": 0.47883597883597884, "acc_stderr": 0.025728230952130733, "acc_norm": 0.47883597883597884, "acc_norm_stderr": 0.025728230952130733 }, "harness|hendrycksTest-formal_logic|5": { "acc": 0.47619047619047616, "acc_stderr": 0.04467062628403273, "acc_norm": 0.47619047619047616, "acc_norm_stderr": 0.04467062628403273 }, "harness|hendrycksTest-global_facts|5": { "acc": 0.47, "acc_stderr": 0.05016135580465919, "acc_norm": 0.47, "acc_norm_stderr": 0.05016135580465919 }, "harness|hendrycksTest-high_school_biology|5": { "acc": 0.7838709677419354, "acc_stderr": 0.02341529343356853, "acc_norm": 0.7838709677419354, "acc_norm_stderr": 0.02341529343356853 }, "harness|hendrycksTest-high_school_chemistry|5": { "acc": 0.5172413793103449, "acc_stderr": 0.035158955511656986, "acc_norm": 0.5172413793103449, "acc_norm_stderr": 0.035158955511656986 }, "harness|hendrycksTest-high_school_computer_science|5": { "acc": 0.71, "acc_stderr": 0.045604802157206845, "acc_norm": 0.71, "acc_norm_stderr": 0.045604802157206845 }, "harness|hendrycksTest-high_school_european_history|5": { "acc": 0.7393939393939394, "acc_stderr": 0.034277431758165236, "acc_norm": 0.7393939393939394, "acc_norm_stderr": 0.034277431758165236 }, "harness|hendrycksTest-high_school_geography|5": { "acc": 0.8282828282828283, "acc_stderr": 0.026869716187429903, "acc_norm": 0.8282828282828283, "acc_norm_stderr": 0.026869716187429903 }, "harness|hendrycksTest-high_school_government_and_politics|5": { "acc": 0.9015544041450777, "acc_stderr": 0.021500249576033463, "acc_norm": 0.9015544041450777, "acc_norm_stderr": 0.021500249576033463 }, "harness|hendrycksTest-high_school_macroeconomics|5": { "acc": 0.6615384615384615, "acc_stderr": 0.02399150050031303, "acc_norm": 0.6615384615384615, "acc_norm_stderr": 0.02399150050031303 }, "harness|hendrycksTest-high_school_mathematics|5": { "acc": 0.3851851851851852, "acc_stderr": 0.029670906124630882, "acc_norm": 0.3851851851851852,
